Definition
Multi-agent learning (MAL) refers to settings in which multiple agents learn simultaneously. Usually defined in a game theoretic setting, specifically in repeated games or stochastic games, the key feature that distinguishes multi-agent learning from single-agent learning is that in the former the learning of one agent impacts the learning of others. As a result, neither the problem definition for multi-agent learning nor the algorithms offered follow in a straightforward way from the single-agent case. In this first of two entries on the subject we focus on the problem definition.
Background
The topic of multi-agent learning (MAL henceforth) has a long history in game theory, almost as long as the history of game theory itself (Another more recent term for the area within game theory is interactive learning). In artificial intelligence (AI) the history of single-agent learning is of course as rich if not richer; one need not look further than this Encyclopedia for...
This is a preview of subscription content, log in via an institution to check access.
Recommended Reading
Requisite background in game theory can be obtained from the many introductory texts, and most compactly from Leyton-Brown (2008). Game theoretic work on multi-agent learning is covered in Fudenberg (1998) and Young (2004). An expanded discussion of the problems addressed under the header of MAL can be found in Shoham et al. (2007), and the responses to it in Vohra (2007). Discussion of MAL algorithms, both traditional and more novel ones, can be found in the above references, as well as in Greenwald (2007).
Fudenberg, D., & Levine, D. (1998). The theory of learning in games. Cambridge: MIT Press.
Greenwald, A., & Littman, M. L. (Eds.). (2007). Special issue on learning and computational game theory. Machine Learning 67(1–2).
Leyton-Brown, K., & Shoham, Y. (2008). Essentials of game theory. San Rafael, CA: Morgan and Claypool.
Shoham, Y., Powers, W. R., & Grenager, T. (2007). If multiagent learning is the answer, what is the question? Artificial Intelligence, 171(1), 365–377. Special issue on foundations of multiagent learning.
Vohra, R., & Wellman, M. P. (Eds.). (2007). Special issue on foundations of multiagent learning. Artificial Intelligence, 171(1).
Young, H. P. (2004). Strategic learning and its limits. Oxford: Oxford University Press.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer Science+Business Media, LLC
About this entry
Cite this entry
Shoham, Y., Powers, R. (2011). Multi-Agent Learning I: Problem Definition. In: Sammut, C., Webb, G.I. (eds) Encyclopedia of Machine Learning. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-30164-8_563
Download citation
DOI: https://doi.org/10.1007/978-0-387-30164-8_563
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-30768-8
Online ISBN: 978-0-387-30164-8
eBook Packages: Computer ScienceReference Module Computer Science and Engineering